Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Karachi
    -0.07
     hak
    -0.07
     kỳ
    -0.07
     Hist
    -0.06
     silly
    -0.06
     Böylece
    -0.06
    HAS
    -0.06
     verbosity
    -0.06
     Henderson
    -0.06
    organisation
    -0.06
    POSITIVE LOGITS
    lbrace
    0.07
     seç
    0.07
    WithIdentifier
    0.06
     Trustees
    0.06
     StatelessWidget
    0.06
    ;"><?
    0.06
     />\
    0.06
    ец
    0.06
    ie
    0.06
     []),↵
    0.06
    Act Density 0.002%

    No Known Activations